Sarath Sreedharan's PhD Proposal (ASU; 7/23/2021)
Slides: https://bit.ly/3y8tNeY
Abstract: The recent breakthroughs in AI have brought the possibility of developing and deploying practical AI systems within our grasp. Though the growing realization that we might soon have people from all walks of life using and working with these systems has also spurred a lot of interest in ensuring that AI systems can efficiently and effectively work and collaborate with their intended users. Chief among the efforts in this direction has been the pursuit of imbuing these agents with the ability to provide intuitive and useful explanations regarding their decisions and actions to end-users. In this proposal, I will describe various works that I have done, and I am currently pursuing as part of my Ph.D. research within the area of explaining sequential decision-making problems. Furthermore, I will frame the discussions of my work within a broader framework to understand and analyze XAI and as we will see, my contributions within this space touch on many of the core challenges related to explaining automated decisions to users including (1) techniques to address asymmetry in knowledge between the user and the system, (2) techniques to address asymmetry in inferential capabilities and finally (3) techniques to address any existing vocabulary mismatch.
0 Comments